Abstract
To
understand
the
processes
behind
pollinator
declines,
and
thus
to
maintain
pollination
efficiency,
we
also
have
fundamental
drivers
influencing
behaviour.
In
this
study,
aim
explore
foraging
behaviour
of
wild
bumblebees,
recognizing
its
importance
from
economic
conservation
perspectives.
We
recorded
Bombus
terrestris
on
Lotus
creticus
,
Persicaria
capitata
Trifolium
pratense
patches
in
five-minute-long
slots
urban
areas
Terceira
(Azores,
Portugal).
For
automated
bumblebee
detection,
created
computer
vision
models
based
a
deep
learning
algorithm,
with
custom
datasets.
achieved
high
F1
scores
0.88
for
0.95
indicating
accurate
detection.
found
that
flower
cover
per
cent,
but
not
plant
species,
influenced
attractiveness
patches,
significant
positive
effect.
There
were
no
differences
between
species
heads.
The
handling
time
was
longer
large-headed
than
those
smaller-headed
.
However,
our
result
did
indicate
bumblebees
spent
flowers
among
three
species.
Here,
justify
vision-based
analysis
as
reliable
tool
studying
behavioural
ecology.
Ecology and Evolution,
Год журнала:
2024,
Номер
14(12)
Опубликована: Ноя. 28, 2024
ABSTRACT
Field
monitoring
plays
a
crucial
role
in
understanding
insect
dynamics
within
ecosystems.
It
facilitates
pest
distribution
assessment,
control
measure
evaluation,
and
prediction
of
outbreaks.
Additionally,
it
provides
important
information
on
bioindicators
with
which
the
state
biodiversity
ecological
integrity
specific
habitats
ecosystems
can
be
accurately
assessed.
However,
traditional
systems
face
various
difficulties,
leading
to
limited
temporal
spatial
resolution
obtained
information.
Despite
recent
advancements
automatic
traps,
also
called
e‐traps,
most
these
focus
exclusively
studying
agricultural
pests,
rendering
them
unsuitable
for
diverse
populations.
To
address
this
issue,
we
introduce
Automatic
Insect
Recognition
(FAIR)‐Device,
novel
nonlethal
field
tool
that
relies
semi‐automatic
image
capture
species
identification
using
artificial
intelligence
via
iNaturalist
platform.
Our
objective
was
develop
an
automatic,
cost‐effective,
nonspecific
solution
capable
providing
high‐resolution
data
assessing
diversity.
During
26‐day
proof‐of‐concept
FAIR‐Device
recorded
24.8
GB
video,
identifying
431
individuals
from
9
orders,
50
families,
69
genera.
While
improvements
are
possible,
our
device
demonstrated
its
potential
as
biodiversity.
Looking
ahead,
envision
new
such
e‐traps
valuable
tools
real‐time
monitoring,
offering
unprecedented
insights
research
practices.
Abstract
To
understand
the
processes
behind
pollinator
declines,
and
thus
to
maintain
pollination
efficiency,
we
also
have
fundamental
drivers
influencing
behaviour.
In
this
study,
aim
explore
foraging
behaviour
of
wild
bumblebees,
recognizing
its
importance
from
economic
conservation
perspectives.
We
recorded
Bombus
terrestris
on
Lotus
creticus
,
Persicaria
capitata
Trifolium
pratense
patches
in
five-minute-long
slots
urban
areas
Terceira
(Azores,
Portugal).
For
automated
bumblebee
detection,
created
computer
vision
models
based
a
deep
learning
algorithm,
with
custom
datasets.
achieved
high
F1
scores
0.88
for
0.95
indicating
accurate
detection.
found
that
flower
cover
per
cent,
but
not
plant
species,
influenced
attractiveness
patches,
significant
positive
effect.
There
were
no
differences
between
species
heads.
The
handling
time
was
longer
large-headed
than
those
smaller-headed
.
However,
our
result
did
indicate
bumblebees
spent
flowers
among
three
species.
Here,
justify
vision-based
analysis
as
reliable
tool
studying
behavioural
ecology.
